pipefy-pipes-and-cards
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Pipefy, such as card titles, comments, and field values, which is a standard operational surface for workflow management tools.\n
- Ingestion points: Data enters the agent's context through tools like
get_card,get_cards, andget_pipe.\n - Boundary markers: The skill does not mandate specific delimiters, although the tool-based architecture inherently structures the data.\n
- Capability inventory: The skill has the capability to modify and delete cards, phases, and pipes within the Pipefy platform.\n
- Sanitization: The instructions do not define specific sanitization or escaping protocols for the platform-provided content.\n- [COMMAND_EXECUTION]: The skill maps operations to a domain-specific CLI and various MCP tools.\n
- Evidence: Operations are executed via commands like
pipefy pipe createandpipefy card move.\n - Safety: Destructive operations, such as deleting pipes or cards, are explicitly marked as requiring user review and approval before execution, often involving a confirmation token mechanism.
Audit Metadata